# Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure

arXiv: https://arxiv.org/abs/2104.08601 · HTML: https://mlsanity.com/paper/2104.08601/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 17 Apr 2021.

## Builds on (most cited first, 10 of 10)

- [Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders](https://mlsanity.com/paper/1703.10960/) (2017)
- [Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions](https://mlsanity.com/paper/1602.01103/) (2016)
- [Discovering Discrete Latent Topics with Neural Variational Inference](https://mlsanity.com/paper/1706.00359/) (2017)
- [Unsupervised Discrete Sentence Representation Learning for Interpretable Neural Dialog Generation](https://mlsanity.com/paper/1804.08069/) (2018)
- [Best of Both Worlds: Transferring Knowledge from Discriminative Learning to a Generative Visual Dialog Model](https://mlsanity.com/paper/1706.01554/) (2017)
- [Joint Modeling of Content and Discourse Relations in Dialogues](https://mlsanity.com/paper/1705.05039/) (2017)
- [What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations](https://mlsanity.com/paper/1903.07319/) (2019)
- [Find the Conversation Killers: a Predictive Study of Thread-ending Posts](https://mlsanity.com/paper/1712.08636/) (2017)
- [Discovering Conversational Dependencies between Messages in Dialogs](https://mlsanity.com/paper/1612.02801/) (2016)
- [A Joint Model of Conversational Discourse and Latent Topics on Microblogs](https://mlsanity.com/paper/1809.03690/) (2018)

## Built on by (most cited first, 1 of 1)

- [Leveraging Large Language Models to Identify Conversation Threads in Collaborative Learning](https://mlsanity.com/paper/2510.22844/) (2025)

## Abstract (arXiv)

Numerous online conversations are produced on a daily basis, resulting in a pressing need to conversation understanding. As a basis to structure a discussion, we identify the responding relations in the conversation discourse, which link response utterances to their initiations. To figure out who responded to whom, here we explore how the consistency of topic contents and dependency of discourse roles indicate such interactions, whereas most prior work ignore the effects of latent factors underlying word occurrences. We propose a model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links via exploiting topic consistency and discourse dependency. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts, such as 79 vs. 73 MRR on Chinese customer service dialogues. We further probe into our outputs and shed light on how topics and discourse indicate conversational user interactions.